Computer implemented methods and apparatus for recommending events

Patent metadata

Field	Value
Publication number	US-9607090-B2
Application number	US-201414160400-A
Country	US
Kind code	B2
Filing date	Jan 21, 2014
Priority date	Jan 21, 2013
Publication date	Mar 28, 2017
Grant date	Mar 28, 2017

Abstract

Disclosed are methods, apparatus, systems, and computer-readable storage media for recommending an event to a user. In some implementations, one or more servers receive information identifying a plurality of events. The one or more servers store data of the plurality of events in a first one or more data tables having an action field, an item field, and a user field, and analyze the data of the first one or more data tables to generate one or more pairs, each pair including information identifying a set of events and a target event. The one or more servers may calculate a similarity score for each of the one or more pairs and store the respective similarity score in a second one or more data tables having a set field, a target event field, and a similarity score field.

First claim

What is claimed is:

1. A system for recommending an event to a user, the system comprising:
a database system implemented using a server system, the server system configured to cause:
processing event data associated with a plurality of events, the event data identifying for each even an action, an item and a user associated with the event;
storing or maintaining the event data using a first one or more data objects of a database of the database system;
determining a plurality of pairs based on the event data using a collaborative filter table, the collaborative filter table identifying a set of events and a target event for each pair, the pairs including a first pair identifying a first set of events and a first target event, the first set of events including an event having a first action of a first action type, the target event having a second action of a second action type, the first action type being different from the second action type;
determining a collaborative filtering similarity for each pair based on at least a frequency of performing the set of events identified by the pair in association with performing the target event of the pair;
storing information identifying the pairs and the respective collaborative filtering similarities using a second one or more data objects of a database of the database system;
processing event information associated with a first user;
identifying, based on the pairs, the respective collaborative filtering similarities and the event information, a first event to be recommended to the first user; and
transmitting, to a computing device associated with the first user, recommendation data for displaying in a user interface on a display of the computing device a recommendation that the first user perform the identified first event.

2. The system of claim 1 , the server system further configured to cause:
transmitting, to the computing device, instructions for arranging or rearranging displayed data and/or user interface components in the user interface to highlight the identified first event.

3. The system of claim 2 , wherein rearranging the displayed data includes repositioning a displayed link in a list of links to an upper region of the list of links, the displayed link representing the identified first event.

4. The system of claim 2 , wherein arranging or rearranging the displayed data includes presenting in the user interface a button or a tab associated with the identified first event.

5. The system of claim 4 , wherein presenting the button or the tab includes positioning the button or the tab at a designated location of the user interface.

6. The system of claim 1 , wherein the events include one or more of: following a user, following a record, clicking a link, joining a group, conversing with a user, accessing a file, acting on a record, acting on a customer relationship management (CRM) object, accessing an image, accessing a video, accessing audio data, communicating with a group or with a user, buying an item, selling an item, performing a search, or following a topic.

7. The system of claim 1 , wherein each action is of an action type, the action type being one of: following, clicking, joining, accessing, downloading, viewing, searching, communicating, buying, selling, recommending, rating, opening, closing, deleting, creating, or updating.

8. The system of claim 1 , wherein an item is one of: a record, a link, an image, a video, a document, a user, a group, a file, a CRM object, a topic, or an article.

9. The system of claim 1 , wherein each set of events includes a sequence of events performed in a particular order by a single user.

10. The system of claim 1 , wherein each set of events includes events performed within a designated time interval by a single user.

11. The system of claim 1 , wherein each set of events has a length being a number of events in the set.

12. The system of claim 11 , wherein the lengths of all of the sets of events are greater than one.

13. The system of claim 1 , wherein the collaborative filtering similarity for a pair is normalized for a frequency that the set of events is performed.

14. The system of claim 1 , wherein the collaborative filtering similarity is based on a cosine-based similarity score.

15. A method for recommending an event to a user, method comprising:
processing, using a database system, event data associated with a plurality of events, the event data identifying for each event an action, an item, and a user associated with the event;
storing or maintaining the event data using a first one or more data objects of a database of the database system;
determining a plurality of pairs based on the event data using a collaborative filter table, the collaborative filter table identifying a set of events and a target event for each pair, the pairs including a first pair identifying a first set of events and a first target event, the first set of events including an event having a first action of a first action type, the target event having a second action of a second action type, the first action type being different from the second action type;
determining a collaborative filtering similarity for each pair based on at least a frequency of performing the set of events identified by the pair in association with performing the target event of the pair;
storing information identifying the pairs and the respective collaborative filtering similarities using a second one or more data objects of a database of the database system;
processing event information associated with a first user;
identifying, based on the pairs, the respective collaborative filtering similarities and the event information, a first event to be recommended to the first user; and
transmitting, to a computing device associated with the first user, recommendation data for displaying in a user interface on a display of the computing device a recommendation that the first user perform the identified first event.

16. The method of claim 15 , further comprising:
transmitting, to the computing device, instructions for arranging or rearranging displayed data and/or user interface components in the user interface to highlight the identified first event.

17. The method of claim 16 , wherein arranging or rearranging the displayed data includes presenting in the user interface a button or a tab associated with the identified first event.

18. The method of claim 17 , wherein presenting the button or the tab includes positioning the button or the tab at a designated location of the user interface.

19. The method of claim 16 , wherein rearranging the displayed data includes repositioning a displayed link in a list of links to an upper region of the list of links, the displayed link representing the identified first event.

20. A computer program product comprising program code to be executed by at least one processor when retrieved from a non-transitory computer-readable storage medium for recommending an event to a user, the program code comprising instructions configured to cause:
processing, using a database system, event data associated with a plurality of events, the event data identifying for each event an action, an item, and a user associated with the event;
storing or maintaining the event data using a first one or more data objects of a database of the database system;
determining a plurality of pairs based on the event data using a collaborative filter table the collaborative filter table identifying a set of events and a target event for eac

Assignees

• Salesforce Com Inc

Inventors

• Palmert Joel
• Meng Xiao

Classifications

• G06F16/24578 Primary

  using ranking · CPC title

• G06F16/22

  Indexing; Data structures therefor; Storage structures · CPC title

• G06F16/248

  Presentation of query results · CPC title

• G06F16/9535 Primary

  Search customisation based on user profiles and personalisation · CPC title

• G06F17/30867 Primary

  Physics · mapped topic